Task-Oriented Dialogue (TOD) systems have become crucial components in interactive artificial intelligence applications. While recent advances have capitalized on pre-trained language models (PLMs), they exhibit limitations regarding transparency and controllability. To address these challenges, we propose a novel approach focusing on inferring the TOD-Flow graph from dialogue data annotated with dialog acts, uncovering the underlying task structure in the form of a graph. The inferred TOD-Flow graph can be easily integrated with any dialogue model to improve its prediction performance, transparency, and controllability. Our TOD-Flow graph learns what a model can, should, and should not predict, effectively reducing the search space and providing a rationale for the model's prediction. We show that the proposed TOD-Flow graph better resembles human-annotated graphs compared to prior approaches. Furthermore, when combined with several dialogue policies and end-to-end dialogue models, we demonstrate that our approach significantly improves dialog act classification and end-to-end response generation performance in the MultiWOZ and SGD benchmarks. Code available at: https://github.com/srsohn/TOD-Flow

翻译：面向任务对话系统已成为交互式人工智能应用中的关键组成部分。尽管近期研究利用预训练语言模型取得了进展，但这些模型在透明性和可控性方面仍存在局限。为解决上述挑战，我们提出了一种新方法，专注于从带有对话行为标注的对话数据中推断TOD-Flow图，以图的形式揭示潜在的任务结构。推断得到的TOD-Flow图可轻松集成至任意对话模型，以提升其预测性能、透明性和可控性。我们的TOD-Flow图能够学习模型可以、应当以及不应当预测的内容，有效缩小搜索空间并为模型预测提供依据。实验表明，与先前方法相比，所提出的TOD-Flow图更接近人工标注的图结构。此外，当与多种对话策略及端到端对话模型结合时，我们的方法在MultiWOZ和SGD基准上显著提升了对话行为分类和端到端响应生成的性能。代码地址：https://github.com/srsohn/TOD-Flow